vasidmi/Wellby-Qwen3.5-0.8B-Base
LoRA-style vs unsloth/Qwen3.5-0.8B-Base. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/129, Attention 114/216, MLP 72/124
1 derivatives checked
- mradermacher/Wellby-Qwen3.5-0.8B-Base-GGUF: Same weights, converted